Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fast Long-Term Multi-Scenario Prediction for Maneuver Planning at Unsignalized Intersections (2401.14879v2)

Published 26 Jan 2024 in cs.RO, cs.SY, and eess.SY

Abstract: Motion prediction for intelligent vehicles typically focuses on estimating the most probable future evolutions of a traffic scenario. Estimating the gap acceptance, i.e., whether a vehicle merges or crosses before another vehicle with the right of way, is often handled implicitly in the prediction. However, an infrastructure-based maneuver planning can assign artificial priorities between cooperative vehicles, so it needs to evaluate many more potential scenarios. Additionally, the prediction horizon has to be long enough to assess the impact of a maneuver. We, therefore, present a novel long-term prediction approach handling the gap acceptance estimation and the velocity prediction in two separate stages. Thereby, the behavior of regular vehicles as well as priority assignments of cooperative vehicles can be considered. We train both stages on real-world traffic observations to achieve realistic prediction results. Our method has a competitive accuracy and is fast enough to predict a multitude of scenarios in a short time, making it suitable to be used in a maneuver planning framework.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (18)
  1. M. Buchholz, J. C. Müller, M. Herrmann, J. Strohbeck, B. Völz, M. Maier, J. Paczia, O. Stein, H. Rehborn, and R.-W. Henn, “Handling Occlusions in Automated Driving Using a Multiaccess Edge Computing Server-Based Environment Model From Infrastructure Sensors,” IEEE Intell. Transp. Syst. Magazine, pp. 2–16, 2021.
  2. K. Dresner and P. Stone, “Multiagent traffic management: a reservation-based intersection control mechanism,” in Proc. of the Third Int. Joint Conf. on Autonomous Agents and Multiagent Syst., 2004. AAMAS 2004., 2004, pp. 530–537.
  3. M. B. Mertens, J. Müller, and M. Buchholz, “Cooperative Maneuver Planning for Mixed Traffic at Unsignalized Intersections Using Probabilistic Predictions,” in 2022 IEEE Intell. Veh. Symp. (IV), 2022, pp. 1174–1180.
  4. M. Klimke, B. Völz, and M. Buchholz, “Automatic Intersection Management in Mixed Traffic Using Reinforcement Learning and Graph Neural Networks,” in preprint, accepted to 2023 IEEE Intell. Veh. Symp., 2023, arXiv:2301.12717.
  5. J. Strohbeck, V. Belagiannis, J. Müller, M. Schreiber, M. Herrmann, D. Wolf, and M. Buchholz, “Multiple Trajectory Prediction with Deep Temporal and Spatial Convolutional Neural Networks,” in 2020 IEEE/RSJ Int. Conf. on Intell. Robots and Syst. (IROS), 2020, pp. 1992–1998.
  6. J. Bock, R. Krajewski, T. Moers, S. Runde, L. Vater, and L. Eckstein, “The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections,” in 2020 IEEE Intell. Veh. Symp. (IV), 2020, pp. 1929–1934.
  7. M. Treiber, A. Hennecke, and D. Helbing, “Congested traffic states in empirical observations and microscopic simulations,” Physical Review E, vol. 62, no. 2, pp. 1805–1824, 2000.
  8. S. Lefèvre, C. Sun, R. Bajcsy, and C. Laugier, “Comparison of parametric and non-parametric approaches for vehicle speed prediction,” in 2014 American Control Conf., 2014, pp. 3494–3499.
  9. J. Erdmann and D. Krajzewicz, “SUMO’s Road Intersection Model,” in Simulation of Urban Mobility, M. Behrisch, D. Krajzewicz, and M. Weber, Eds.   Springer Berlin Heidelberg, 2014, pp. 3–17.
  10. Abhishek, M. A. A. Boon, and M. Mandjes, “Generalized gap acceptance models for unsignalized intersections,” Mathematical Methods of Operations Research, vol. 89, no. 3, pp. 385–409, 2019.
  11. Y. Duan, X. Chen, R. Houthooft, J. Schulman, and P. Abbeel, “Benchmarking Deep Reinforcement Learning for Continuous Control,” 2016, arXiv:1604.06778.
  12. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal Policy Optimization Algorithms,” 2017, arXiv:1707.06347.
  13. A. Kuefler, J. Morton, T. Wheeler, and M. Kochenderfer, “Imitating driver behavior with generative adversarial networks,” in 2017 IEEE Intell. Veh. Symp. (IV), 2017, pp. 204–211.
  14. M. Sackmann, H. Bey, U. Hofmann, and J. Thielecke, “Modeling Driver Behavior using Adversarial Inverse Reinforcement Learning,” in 2022 IEEE Intell. Veh. Symp. (IV), 2022, pp. 1683–1690.
  15. J. Ho and S. Ermon, “Generative Adversarial Imitation Learning,” 2016, arXiv:1606.03476.
  16. J. Strohbeck, J. Müller, A. Holzbock, and M. Buchholz, “DeepSIL: A Software-in-the-Loop Framework for Evaluating Motion Planning Schemes Using Multiple Trajectory Prediction Networks,” in 2021 IEEE/RSJ Int. Conf. on Intell. Robots and Syst. (IROS), 2021, pp. 7075–7081.
  17. K. Kurzer, C. Zhou, and J. Marius Zöllner, “Decentralized Cooperative Planning for Automated Vehicles with Hierarchical Monte Carlo Tree Search,” in 2018 IEEE Intell. Veh. Symp. (IV), 2018, pp. 529–536.
  18. M. Sackmann, H. Bey, U. Hofmann, and J. Thielecke, “Classification of Driver Intentions at Roundabouts,” in Proc. of the 6th Int. Conf. on Veh. Technol. and Intell. Transport Syst.   SCITEPRESS - Sci. and Technol. Publications, 2020, pp. 301–311.

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com